Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization Jurnal Ilmiah Teknik Industri Jurnal Senopati : Sustainability, Ergonomics, Optimization, and Application of Industrial Engineering Journal of Production, Enterprise, and Industrial Applications Proceeding of Community Service and Engagement
Aulia Dihas Zahira
Telkom University
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Engineering Industrial & Manufacturing Engineering Transportation

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Development of Automatic Object Detection and IoT for Garbage Pickup Assignment Problem Bayu Setyawan, Erlangga; Novitasari, Nia; Zahira, Aulia Dihas
JOIV : International Journal on Informatics Visualization Vol 8, No 2 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.2.2740

Abstract

Waste management remains a challenge in certain cities, particularly in allocating fleets responsible for collecting garbage from temporary disposal sites. Inadequate planning can lead to the accumulation of substantial waste piles. This study aims to enhance truck assignment by considering truck capacity and the collection route. The assignment process incorporates the fundamental concept of the transportation problem, precisely the northwest corner method. The volume of waste transported aligns with the resident or industrial population within the designated service area. The waste generation capacity determines the future fleet and quantity, forming a crucial element of the ensuing distribution channel. A monitoring system integrating object detection and the Internet of Things (IoT) has been devised to ensure effective garbage collection. Cameras strategically positioned at temporary disposal sites transmit real-time images. The system evaluates garbage collection capacity through object detection facilitated by neural network training. The research outcomes demonstrate the system's capability to identify waste pile levels and validate the garbage pickup process by the designated fleet. Future research should focus on assignment and scheduling in waste transportation, enabling fleet allocation within specific timeframes. Additionally, an object detection algorithm refinement is necessary for more precise identification of waste pile locations.
Optimalisasi Rute Distribusi Produk Frozen Untuk Meminimasi Biaya Transportasi dan Gas Emisi Pada PT. Sukanda Djaya Dengan Metode Algoritma Genetika Aulia Dihas Zahira; Erlangga Bayu Setyawan; Yudha Prambudia
Journal of Production, Enterprise, and Industrial Applications Vol. 2 No. 2 (2024): Desember 2024
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jpeia.v2i2.8719

Abstract

PT. Sukanda Djaya merupakan distributorproduk frozen dari perusahaan PT. Diamond Cold Storage yangmemproduksi produk seperti susu,yoghurt,daging, dan lainlain. Pendistribusian produk dilakukan pada 25 agen konsumendengan menggunakan empat unit kendaraan bermuatanmasing-masing 6,5 ton. Permasalahan yang terjadi adalahperusahaan tidak memiliki rute tetap untuk mendistribusikanproduk nya, yang berakibat adanya produk return dari agenkonsumen kembali ke depot dikarenakan kualitas produkmenurut saat tiba di agen konsumen. Permasalah tersebutterjadi karena lamanya waktu tempuh dikarenakan tidakadanya rute tetap.Pendistribusian produk frozen menggunakan trukberpendingin juga mempengaruhi konsumsi gas emisi yangdihasilkan, karena truk berpendingin menghasilkan 30% gasemisi CO2 lebih tinggi dibandingkan dengan truk biasa.Pengurangan biaya transportasi dan gas emisi dapat dilakukandengan menentukan rute usulan untuk proses distribusi yangefektif dan efisien. Berdasarkan masalah yang terjadi,dilakukan penentuan rute dengan menggunakan metodealgoritma genetika.Hasil yang diperoleh yaitu dengan adanya rute usulan yangdihasilkan menggunakan metode algoritma genetika terjadiminimasi biaya transportasi sebesar 79,35% dan tidak adanyaproduk return yang dihasilkan karena waktu tempuh setiapkendaraan tidak ada yang melebihi waktu shelf life produkyaitu 120 menit.
IMPLEMENTASI KEBIJAKAN PENGISIAN ULANG YANG OPTIMAL PADA GONDOLA MENGGUNAKAN METODE NON-LINEAR INTEGER PROGRAMMING PADA SUPERMARKET XYZ Prafajar Suksessanno Muttaqin; Erlangga Bayu Setyawan; Nia Novitasari; Aulia Dihas Zahira; Yoara Damar Puspasari; Dhea Cantika Febriyanti; Denisse Michelle Gunawan
The Proceeding of Community Service and Engagement (COSECANT) Seminar Vol. 4 No. 1 (2024): The Proceeding of Community Service and Engagement (COSECANT) Seminar
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/cosecant.v6i1.7903

Abstract

Supermarket XYZ menghadapi tantangan serius yang mempengaruhi profitabilitasnya. Kegiatan abdimas ini bertujuan untuk menganalisis faktor-faktor utama yang menyebabkan penurunan profit dalam supermarket. Faktor-faktor tersebut meliputi stock out (kehabisan stok), biaya display yang tinggi, investasi tinggi dalam inventory (persediaan), biaya pemesanan yang tinggi, dan biaya penyimpanan yang tinggi. Penelitian ini dilakukan melalui analisis data historis dari Supermarket XYZ, termasuk catatan tentang tingkat stok yang tidak mencukupi, biaya pengeluaran untuk display produk, investasi dalam persediaan, biaya pemesanan, dan biaya penyimpanan. Hasil analisis data menunjukkan bahwa stock out secara konsisten mengakibatkan hilangnya penjualan dan pelanggan yang kecewa. Biaya display yang tinggi, meskipun memberikan tampilan produk yang menarik, telah meningkatkan biaya operasional supermarket tanpa pencapaian yang seimbang dalam peningkatan penjualan. Investasi yang tinggi dalam persediaan menyebabkan dana yang terikat dalam stok yang tidak produktif, sementara biaya pemesanan yang tinggi dan biaya penyimpanan yang tinggi membebani profitabilitas dengan cara yang signifikan. Berdasarkan permasalahan yang dimiliki oleh Supermarket XYZ maka dilakukan pemaksimalan penggunaan gondola. Kegiatan abdimas ini dilakukan untuk memberikan usulan pengisiian ulang gondola dengan menggunakan metode Nonlinear Integer Programming yang bertujuan untuk memaksimalkan total net profit pada Supermarket XYZ. Adapun hasil penerapan metode usulan adalah total produk di display dan total produk yang ditampilkan pada showroom.
IMPLEMENTASI MODEL PERSEDIAAN MULTI-ITEM PROBABILISTIK BERBASIS KADALUWARSA UNTUK MENURUNKAN TOTAL BIAYA PADA INDUSTRI FMCG Aulia Dihas Zahira; Erlangga Bayu Setyawan
Jurnal Ilmiah Teknik Industri Vol. 13 No. 3 (2025): Jurnal Ilmiah Teknik Industri : Jurnal Keilmuan Teknik dan Manajemen Industri
Publisher : Program Studi Teknik Industri, Fakultas Teknik Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/jitiuntar.v13i3.37281

Abstract

Inventory management in the Fast-Moving Consumer Goods (FMCG) sector is challenged by high demand volatility, limited storage capacity, and product perishability, all pf which substantially increase operational costs when not properly controlled. These challenges become more severe when ordering decisions are made without a structured policy and are influenced by quantity-based discounts that may unintentionally raise inventory levels and expiration risks. This study aims to develop probabilistic multi-item inventory levels and expiration risks. This study aims to develop a probabilistic multi-item inventory model that explicitly incorporates perishability factors to generate optimal replenishment decision under stochastic demand conditions. The methodology includes identifying demand distribution patterns using the Kolmogorov-Smirnov goodness test, forecasting demand through Simple Exponential Smoothing, Holt’s Method, and Linear Trend Models, and integrating the results into a contemporary probabilistic inventory control model that considers storage capacity, discount schemes, and shortage risks. A numerical study involving seven products over a 12-month horizon is conducted to empirically evaluate the model’s performance. The results demonstrate that the proposed model significantly reduces total inventory cost, with notable decreases across purchasing, ordering, holding, shortage, and expiration cost components, achieving cost reductions exceeding 70% compared to the initial condition. The model provides precise value for optimal ordering time (T*), order quantity (Q), and safety stock, offering a robust and practical decision support framework for FMCG companies. These findings reinforce the importance of integrating perishability and capacity constraints into probabilistic inventory models to enhance decision quality and operational efficiency.
Prediksi Preferensi Waktu Pengiriman Pelanggan Untuk Optimalisasi Layanan Logistik Menggunakan Decision Tree Femi Yulianti; Aulia Dihas Zahira
Jurnal SENOPATI : Sustainability, Ergonomics, Optimization, and Application of Industrial Engineering Vol 7, No 2 (2026): Jurnal SENOPATI Vol 7, No 2
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.senopati.2026.v7i2.8113

Abstract

In the era of customer-centric logistics, the ability to predict delivery time preferences is critical to enhancing service quality and operational efficiecy. This study proposes a predictive analytics framework to classify customer-preferred delivery times – morning, afternoon, evening, or night – using historical logistics data and customer perception analysis. Utilizing the Amazon delivery dataset, categorical time intervals were derived through timestamp transformation, enabling classification modeling with three machine learning algorithms Naive bayes, Logistic regression, and Decision tree. Among these, the Decision tree algorithm yielded the best performance, achieving an accuracy of 77% and a macro F1-score of 0.77. Further analysis revealed that traffic conditions, vehicle types, and product categories were the most influential features in predicting delivery time preference. Survei results corroborated the model’s findings, with customer responses highlighting traffic and delivery timing as top priorities for service satisfaction. This research demonstrates the integration of data-driven modeling with customer insights to support decision-making in last-mile logistics. The findings can guide logistics providers in designing adaptive, preference-based delivery schedules that improve service realiability and user experience.Keywords: predictive analytics, delivery time preference, decision tree, last-mile logistics, customer satisfaction, machine learning.
Co-Authors Denisse Michelle Gunawan Dhea Cantika Febriyanti Erlangga Bayu Setyawan Nia Novitasari Prafajar Suksessanno Muttaqin Prambudia, Yudha Yoara Damar Puspasari Yulianti, Femi